Weather Forecasting Using Decision Tree
In one sentence. Decision tree methods, including M5P, REP Tree and Random Forest, forecast daily maximum and minimum temperature in Delhi from 17 months of data. Random Forest is best.
Abstract
The present situation of climate change calls for the need to develop a system which can forecast temperature in advance so that it can be helpful for making polices by government. Decision Trees is a method used to analyse combination of Mathematical & Computational Techniques in order to make description, categorisation & generalisation of given set of data using machine learning to predict behaviour for future performance. In this study the Decision Tree techniques like Quinlan's M5 algorithm (M5P), Reduced Error Pruning Tree (REP Tree), Random Forest, Logit Boosting, Ada Boosting M1Tool are used to analyse the weather parameter Maximum Temperature and Minimum Temperature for Delhi region. Daily data set of 17 months has been used for analysing and forecasting. It is observed that among the techniques of decision tree; Random Forest is much effective than statistical methods as it gives better results in less time and less statistical errors.
Labels
- Topic
- Local & station forecasting
- Type
- Evaluation or intercomparison of existing models
- Method
- Classical ML (trees, GP, linear, kernels)
- Time scale
- 6 h–3 days
- Domain
- Local / station
- Data
- Station / in-situ
- Status
- Research
- Identifiers
- DOI:10.36909/jer.iccemme.15635 OpenAlex:W3213003852
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.